© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 71034
    Prev
    Next
    INDEX
    Explanations

    USB drives/removable media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     facelift
    -0.09
     underwriting
    -0.09
     skyline
    -0.09
    buyers
    -0.08
     nitric
    -0.08
     synthesis
    -0.08
     lask
    -0.08
     financing
    -0.08
     redevelopment
    -0.08
     nug
    -0.08
    POSITIVE LOGITS
    _USB
    0.10
    Portable
    0.10
     Arduino
    0.10
     disc
    0.09
    usb
    0.09
     Portable
    0.09
     unplug
    0.09
    DISC
    0.09
     EEPROM
    0.08
     portable
    0.08
    Activations Density 0.018%

    No Known Activations